DOI: 10.1161/circ.148.suppl_1.17865 ISSN: 0009-7322

Abstract 17865: Machine Learning With Multimodal Pre Ablation Imaging for Predicting Recurrence in Atrial Fibrillation Patients

Abhishek Midya, Golnoush Asaeikheybari, Amogh Hiremath, Vidya Sankar Viswanathan, Han Sun, Samuel Harwood, Hyun Su Kim, Taylor Schilling, William Telfer, Alison Jin, Justin Baraboo, Maurice Pradella, Michael Markl, Rod S Passman, Majd El-Harasis, Ben B Shoemaker, Animesh A Tandon, John Barnard, Mina K Chung, Anant Madabhushi
  • Physiology (medical)
  • Cardiology and Cardiovascular Medicine

Purpose: Catheter ablation is a popular treatment option for atrial fibrillation (AF), but AF recurrence is common. Currently, no marker exists to reliably predict the risk or location of recurrence (AF+). In this work, a multimodal imaging approach was employed to identify surface of interest (SOI) associated with recurrence using pre-ablation MRI and CT scans.

Hypothesis: Shape of the left atrium (LA) plays a critical role in AF recurrence. The difference between AF+ and AF- may be identified on pre-ablation scan and may find potential sites for additional pre-emptive ablation. Method: Two representative template scans were selected from each group and all patients were registered to these respective templates to develop an atlas for each group. The two atlases were then co-registered, and the difference areas were obtained using a t-test with 500 permutations. The SOI was identified as the area that showed statistically significant (p <0.05) differences between the AF+ and AF-. The process was repeated 5 times to obtain most frequent SOI. Since no ground truth for SOI exists, we used a multimodal imaging approach to construct atlases on CT and MRI; the corresponding SOIs were compared.

Results: 102 CT (51 AF+) and 160 MRI (79 AF+) scans collected from Cleveland Clinic and Vanderbilt University were randomly sampled 5 times. At each iteration 20 patients from AF+ and AF- patients were randomly chosen and employed to create atlases for generating SOIs. The dice sore of MRI and CT derived SOI were 0.75± 0.08 and 0.82±0.05, respectively. The SOI region was below the LA appendage and left inferior pulmonary vein on both CT and MRI. The ratio of significant region to LA volume were [9%-18%] and [8%-19%] for CT and MRI, respectively indicating a good agreement between two SOIs.

Conclusion: We identified SOI associated with AF+ from CT and MRI and found correlation between them at sites expected to be near the vein of Marshall, an area increasingly targeted for recurrent AF after prior ablation.

More from our Archive